IEEE Transactions on Very Large Scale Integration (VLSI) Systems
A predictive system shutdown method for energy saving of event-driven computation
ICCAD '97 Proceedings of the 1997 IEEE/ACM international conference on Computer-aided design
Dynamic power management of complex systems using generalized stochastic Petri nets
Proceedings of the 37th Annual Design Automation Conference
A survey of design techniques for system-level dynamic power management
IEEE Transactions on Very Large Scale Integration (VLSI) Systems - Special section on low-power electronics and design
Hierarchical power management with application to scheduling
ISLPED '05 Proceedings of the 2005 international symposium on Low power electronics and design
Stochastic modeling and optimization for robust power management in a partially observable system
Proceedings of the conference on Design, automation and test in Europe
Dynamic power management under uncertain information
Proceedings of the conference on Design, automation and test in Europe
Policy optimization for dynamic power management
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Adaptive power management using reinforcement learning
Proceedings of the 2009 International Conference on Computer-Aided Design
Power-aware performance increase via core/uncore reinforcement control for chip-multiprocessors
Proceedings of the 2012 ACM/IEEE international symposium on Low power electronics and design
Achieving autonomous power management using reinforcement learning
ACM Transactions on Design Automation of Electronic Systems (TODAES)
Hi-index | 0.00 |
The effectiveness of stochastic power management relies on the accurate system and workload model and effective policy optimization. Workload modeling is a machine learning procedure that finds the intrinsic pattern of the incoming tasks based on the observed workload attributes. Markov Decision Process (MDP) based model has been widely adopted for stochastic power management because it delivers provable optimal policy. Given a sequence of observed workload attributes, the hidden Markov model (HMM) of the workload is trained. If the observed workload attributes and states in the workload model do not have one-to-one correspondence, the MDP becomes a Partially Observable Markov Decision Process (POMDP). This paper presents a framework of modeling and optimization for stochastic power management using HMM and POMDP. The proposed technique discovers the HMM of the workload by maximizing the likelihood of the observed attribute sequence. The POMDP optimization is formulated and solved as a quadraticly constrained linear programming (QCLP). Compared with traditional optimization technique, which is based on value iteration, the QCLP based optimization provides superior policy by enabling stochastic control.